Commit Graph

Select branches

Hide Pull Requests

AIE-86/notify-errors-via-sse

AIE-87/model-not-found-on-rm

add-distribution-initializer

adds-makefile

bump-model-distribution

bump-model-distribution-progress

dockerize

dorin.geman/llamacpp-paths

force-delete

gitignore

handle-missing-dir

improvements

main

main.go

openai-passthrough

ps-beter-server-error

ps-better-estimation-error

ps-enable-fa

ps-fix-auto-update

ps-no-warmup

ps-win-arm64-support

revert-11-tag-model

support-registry-in-model-name

tag-and-push

tag-model

untagged-openai-models

#1

#10

#100

#101

#102

#103

#104

#105

#106

#107

#11

#110

#111

#112

#113

#115

#116

#117

#119

#12

#120

#123

#124

#125

#128

#129

#13

#133

#134

#135

#136

#137

#14

#142

#144

#145

#146

#147

#148

#148

#149

#15

#16

#17

#18

#19

#2

#20

#21

#22

#23

#24

#26

#27

#28

#29

#3

#30

#31

#32

#33

#34

#35

#36

#37

#38

#39

#4

#40

#41

#42

#43

#44

#44

#45

#46

#47

#47

#48

#48

#49

#5

#50

#51

#52

#53

#54

#55

#56

#57

#58

#59

#6

#60

#61

#62

#63

#65

#66

#67

#68

#69

#7

#70

#72

#73

#74

#75

#76

#77

#78

#79

#8

#80

#81

#83

#85

#86

#87

#88

#89

#9

#91

#92

#93

#94

#95

#96

#98

#99

Mono Color

• 257c9cccd4
  Merge pull request #2 from thaJeztah/migrate_containerd_v2 Dorin-Andrei Geman 2025-04-08 12:03:32 +0300
• 795693e560
  pkg/internal/dockerhub: migrate to containerd v2 Sebastiaan van Stijn 2025-04-07 17:24:27 +0200
• 473b9df71e llama.cpp: Pass server storage paths as parameters Dorin Geman 2025-04-02 17:29:10 +0300
• dccbd7ee30 llama.cpp: Pass server storage paths as parameters dorin.geman/llamacpp-paths Dorin Geman 2025-04-02 17:29:10 +0300
• 184f9c426b
  inference: remove platform support detection Jacob Howard 2025-03-28 18:26:04 -0600
• 36ae1e3b30
  inference: adjust for lack of logger and paths packages Jacob Howard 2025-03-28 17:41:41 -0600
• 10a7de56cd
  deps: update go.mod and add go.sum Jacob Howard 2025-03-28 16:03:03 -0600
• 95ad19a481
  deps: vendor utility dependencies Jacob Howard 2025-03-28 15:23:38 -0600
• bd68cb37ef
  chore: add go.mod Jacob Howard 2025-03-28 15:23:56 -0600
• f7cec84173
  deps: remove errordef package references Jacob Howard 2025-03-28 15:09:10 -0600
• eab81f859f
  inference: use system proxy and enforce RAM for model pulls Jacob Howard 2025-03-25 14:53:04 -0600
• 1d903ff29d
  inference: Retry backend install if it failed due to context.Canceled Dorin Geman 2025-03-22 12:11:31 +0200
• fbf1e0f579
  inference: Add temporary mechanism for dynamic installation Dorin Geman 2025-03-22 10:48:37 +0200
• 97bc6085e6
  List models following OpenAI API spec Ignasi 2025-03-20 13:51:35 +0100
• eef6a7df7c
  flusher can't be nil at this point Ignasi 2025-03-19 18:27:53 +0100
• 9232cb2634
  Ensure flusher is not nil Ignasi 2025-03-19 17:13:58 +0100
• 0ea001602d
  Error handling when pulling models: - Handle invalid reference - Handle model not found Ignasi 2025-03-19 14:17:09 +0100
• 2ddd3a57d8
  Update usages of model-distribution Ignasi 2025-03-18 23:37:52 +0100
• 4c46f589d7
  inference: Supported on darwin/arm64 only Dorin Geman 2025-03-14 11:13:21 +0200
• 2bbd26fdeb
  Move prefix paths to inference package Ignasi 2025-03-12 11:36:36 +0100
• 60bc8a5641
  Add models prefix to fix telemetry Ignasi 2025-03-12 10:47:21 +0100
• 348832f7d0
  - Removes inference prefix from model manager related endpoints - Adds model_manager_test.go - Removes json suffix from path Ignasi 2025-03-11 22:32:22 +0100
• 15afbbac49
  Extract to common variable to not repeat the prefix Ignasi 2025-03-11 13:12:48 +0100
• 7878bc7c69
  From ml.docker.internal to model-runner.docker.internal Ignasi 2025-03-10 16:50:51 +0100
• 55843c8685
  Adds --jinja to provide tool calling support Ignasi 2025-03-12 14:11:30 +0100
• b33e90ec75
  inference: models: Fix download progress streaming Dorin Geman 2025-03-07 13:09:01 +0200
• 4865beb2c3
  Fix IT Ignasi 2025-03-06 17:09:02 +0100
• 7a1cf900d1
  fix format Ignasi 2025-03-06 16:03:22 +0100
• 70e59ffd36
  Potential fix for code scanning alert no. 459: Reflected cross-site scripting Ignasi 2025-03-06 15:54:51 +0100
• 1c24c91ea9
  Sort imports Ignasi 2025-03-06 15:38:36 +0100
• c5904eaec9
  Show progress on pulling to caller Ignasi 2025-03-06 15:33:31 +0100
• 837da6d3a7
  Fix type Ignasi 2025-03-06 15:24:31 +0100
• e64f4a9343
  Removes repeated types Ignasi 2025-03-06 14:03:46 +0100
• 2b22896c95
  Handle case where distributionClient can not be initialized Ignasi 2025-03-06 13:47:26 +0100
• c7dd57bbc2
  Logs pull progress Ignasi 2025-03-06 13:39:39 +0100
• 99af02a4f9
  No need to use different implementations for pull models between win/unix for now Ignasi 2025-03-06 12:10:37 +0100
• ab0738b920
  GetModel must be public Ignasi 2025-03-05 21:40:05 +0100
• c46c97c14d
  Simplify getModels Ignasi 2025-03-05 20:13:14 +0100
• a83b8e49bf
  Applies gofumpt Ignasi 2025-03-05 16:18:26 +0100
• d6423dfae7
  Fixes e2e Ignasi 2025-03-05 15:05:44 +0100
• b69d84f8aa
  Using model distribution client Ignasi 2025-03-04 22:00:57 +0100
• f1c25bd9a2
  Use get models from distribution client Ignasi 2025-03-04 13:09:24 +0100
• 1f90aa3456
  Adds model distribution client Ignasi 2025-03-04 10:41:30 +0100
• ac5324bd3a
  [AIE-52] inference: add separate completion/embedding backend modes Jacob Howard 2025-03-05 11:52:37 -0700
• fe715cd9e6
  inference: add routes for a default inference backend Jacob Howard 2025-03-03 15:58:30 -0700
• dba8db4f8f
  [AIE-41] inference: disable automatic model pulls on inference calls Jacob Howard 2025-03-04 12:27:03 -0700
• 4403a2a9f9
  inference: hide and disable inference services on unsupported platforms Jacob Howard 2025-02-28 17:49:10 -0700
• 910f9350f9
  inference: disable pulls on Windows pending docker/model-distribution Jacob Howard 2025-02-28 11:16:50 -0700
• 9abc853ec3
  inference: Bump llama.cpp runtime to 0.0.0-experimental2 Piotr Stankiewicz 2025-02-28 08:38:10 +0100
• 3201fb5049
  inference: Update telemetry Dorin Geman 2025-02-27 16:28:19 +0200
• 7a93a6e3db
  inference: disable llama.cpp installs on unsupported platforms Jacob Howard 2025-02-27 09:31:00 -0700
• 7c351f6aa0
  inference: add minor optimization to loader Jacob Howard 2025-02-27 04:32:38 -0700
• 5c7f902bfe
  inference/llamacpp: Remove socket before starting Dorin Geman 2025-02-27 13:15:27 +0200
• ae9d65a364
  inference: Installer only runs once Dorin Geman 2025-02-27 13:14:35 +0200
• 0f6f2f863c
  inference: Tiny loader fix Dorin Geman 2025-02-27 13:13:37 +0200
• 7f7aa129fa
  inference/llamacpp: Remove debug log Dorin Geman 2025-02-27 11:03:02 +0200
• 69971fb598
  inference: two small fixes to the scheduler Jacob Howard 2025-02-27 03:35:21 -0700
• 348f46991c
  inference: wire up model deletion endpoint Jacob Howard 2025-02-26 16:45:42 -0700
• d6b1191a01
  inference: refactor scheduler to a more modular design Jacob Howard 2025-02-26 16:03:32 -0700
• a14517d6bf
  inference: Add stub for llama.cpp backend Dorin Geman 2025-02-26 19:30:58 +0200
• 8dd1f8dbce
  inference/scheduler: Cancel backend context to avoid leaks Dorin Geman 2025-02-25 15:32:27 +0200
• c8a97ae68d
  inference: Require "model" field for completion or embedding Dorin Geman 2025-02-25 14:27:20 +0200
• 842ce2ddbb
  inference: Handle /v1/completions Dorin Geman 2025-02-25 14:09:31 +0200
• 450b828845
  inference: Register /models/{namespace}/{name} Dorin Geman 2025-02-25 13:55:03 +0200
• f8cdbc4d81
  inference: refactor service and implement scheduling mechanism Jacob Howard 2025-02-24 20:05:35 -0700
• 21e10c378a
  inference: move to modular backend structure and implement stubs Jacob Howard 2025-02-19 15:16:30 -0700